Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01427628c06603d856d6b98a24e2f44f5c0d61ac4690dc8ece9c4e208eb0e82f
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d7aea13fe9ff43f2e8eab3e87d2db423268a98e92b948f8ba428184ae1ccb3
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 196096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,902 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2493,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00802447464767541,
+      "grad_norm": 1.7389945502862767,
+      "learning_rate": 3.8e-06,
+      "loss": 0.4595,
+      "step": 20
+    },
+    {
+      "epoch": 0.01604894929535082,
+      "grad_norm": 1.21721434066401,
+      "learning_rate": 7.8e-06,
+      "loss": 0.34,
+      "step": 40
+    },
+    {
+      "epoch": 0.02407342394302623,
+      "grad_norm": 1.4115052448687924,
+      "learning_rate": 1.18e-05,
+      "loss": 0.3013,
+      "step": 60
+    },
+    {
+      "epoch": 0.03209789859070164,
+      "grad_norm": 1.1854124218870574,
+      "learning_rate": 1.58e-05,
+      "loss": 0.2841,
+      "step": 80
+    },
+    {
+      "epoch": 0.04012237323837705,
+      "grad_norm": 1.0821081494365905,
+      "learning_rate": 1.9800000000000004e-05,
+      "loss": 0.2679,
+      "step": 100
+    },
+    {
+      "epoch": 0.04814684788605246,
+      "grad_norm": 1.1396877768521696,
+      "learning_rate": 2.38e-05,
+      "loss": 0.2983,
+      "step": 120
+    },
+    {
+      "epoch": 0.05617132253372787,
+      "grad_norm": 0.8863724861851471,
+      "learning_rate": 2.7800000000000005e-05,
+      "loss": 0.2976,
+      "step": 140
+    },
+    {
+      "epoch": 0.06419579718140328,
+      "grad_norm": 1.1286540636393274,
+      "learning_rate": 3.18e-05,
+      "loss": 0.3047,
+      "step": 160
+    },
+    {
+      "epoch": 0.07222027182907868,
+      "grad_norm": 1.6326246678745442,
+      "learning_rate": 3.58e-05,
+      "loss": 0.314,
+      "step": 180
+    },
+    {
+      "epoch": 0.0802447464767541,
+      "grad_norm": 1.012185268707376,
+      "learning_rate": 3.9800000000000005e-05,
+      "loss": 0.3085,
+      "step": 200
+    },
+    {
+      "epoch": 0.0882692211244295,
+      "grad_norm": 0.8913802081695356,
+      "learning_rate": 4.38e-05,
+      "loss": 0.3193,
+      "step": 220
+    },
+    {
+      "epoch": 0.09629369577210492,
+      "grad_norm": 0.9943286125063995,
+      "learning_rate": 4.78e-05,
+      "loss": 0.3397,
+      "step": 240
+    },
+    {
+      "epoch": 0.10431817041978032,
+      "grad_norm": 1.9971168907457575,
+      "learning_rate": 4.999801376569132e-05,
+      "loss": 0.3527,
+      "step": 260
+    },
+    {
+      "epoch": 0.11234264506745574,
+      "grad_norm": 0.8841449553244364,
+      "learning_rate": 4.9979380055256516e-05,
+      "loss": 0.3249,
+      "step": 280
+    },
+    {
+      "epoch": 0.12036711971513114,
+      "grad_norm": 0.7868550214589912,
+      "learning_rate": 4.99411464181739e-05,
+      "loss": 0.342,
+      "step": 300
+    },
+    {
+      "epoch": 0.12839159436280656,
+      "grad_norm": 0.8832077761817314,
+      "learning_rate": 4.988334285424654e-05,
+      "loss": 0.3471,
+      "step": 320
+    },
+    {
+      "epoch": 0.13641606901048198,
+      "grad_norm": 0.83820196705535,
+      "learning_rate": 4.980601471870785e-05,
+      "loss": 0.346,
+      "step": 340
+    },
+    {
+      "epoch": 0.14444054365815737,
+      "grad_norm": 0.9195620174146593,
+      "learning_rate": 4.970922268663387e-05,
+      "loss": 0.341,
+      "step": 360
+    },
+    {
+      "epoch": 0.15246501830583278,
+      "grad_norm": 0.8652054536281212,
+      "learning_rate": 4.9593042705334926e-05,
+      "loss": 0.3415,
+      "step": 380
+    },
+    {
+      "epoch": 0.1604894929535082,
+      "grad_norm": 0.7223602683001062,
+      "learning_rate": 4.945756593476401e-05,
+      "loss": 0.34,
+      "step": 400
+    },
+    {
+      "epoch": 0.16851396760118362,
+      "grad_norm": 0.7592581825293532,
+      "learning_rate": 4.9302898675988616e-05,
+      "loss": 0.3454,
+      "step": 420
+    },
+    {
+      "epoch": 0.176538442248859,
+      "grad_norm": 0.8985377633784642,
+      "learning_rate": 4.912916228778228e-05,
+      "loss": 0.354,
+      "step": 440
+    },
+    {
+      "epoch": 0.18456291689653442,
+      "grad_norm": 0.8407832804783139,
+      "learning_rate": 4.893649309140107e-05,
+      "loss": 0.3381,
+      "step": 460
+    },
+    {
+      "epoch": 0.19258739154420984,
+      "grad_norm": 0.7817366357087974,
+      "learning_rate": 4.8725042263619896e-05,
+      "loss": 0.3384,
+      "step": 480
+    },
+    {
+      "epoch": 0.20061186619188526,
+      "grad_norm": 0.7998744498632891,
+      "learning_rate": 4.849497571811257e-05,
+      "loss": 0.3433,
+      "step": 500
+    },
+    {
+      "epoch": 0.20863634083956065,
+      "grad_norm": 0.7366878614464625,
+      "learning_rate": 4.824647397526854e-05,
+      "loss": 0.332,
+      "step": 520
+    },
+    {
+      "epoch": 0.21666081548723606,
+      "grad_norm": 0.9257245781477709,
+      "learning_rate": 4.797973202054865e-05,
+      "loss": 0.3578,
+      "step": 540
+    },
+    {
+      "epoch": 0.22468529013491148,
+      "grad_norm": 0.7229221912787754,
+      "learning_rate": 4.769495915149091e-05,
+      "loss": 0.3318,
+      "step": 560
+    },
+    {
+      "epoch": 0.2327097647825869,
+      "grad_norm": 0.7896861351942223,
+      "learning_rate": 4.7392378813486374e-05,
+      "loss": 0.3239,
+      "step": 580
+    },
+    {
+      "epoch": 0.2407342394302623,
+      "grad_norm": 0.7057182651650622,
+      "learning_rate": 4.707222842445401e-05,
+      "loss": 0.3367,
+      "step": 600
+    },
+    {
+      "epoch": 0.2487587140779377,
+      "grad_norm": 0.7646297450840412,
+      "learning_rate": 4.6734759188552116e-05,
+      "loss": 0.3345,
+      "step": 620
+    },
+    {
+      "epoch": 0.2567831887256131,
+      "grad_norm": 0.8144984197146983,
+      "learning_rate": 4.638023589907239e-05,
+      "loss": 0.3264,
+      "step": 640
+    },
+    {
+      "epoch": 0.26480766337328854,
+      "grad_norm": 0.799665735836617,
+      "learning_rate": 4.6008936730671414e-05,
+      "loss": 0.339,
+      "step": 660
+    },
+    {
+      "epoch": 0.27283213802096395,
+      "grad_norm": 0.888997665044708,
+      "learning_rate": 4.562115302110254e-05,
+      "loss": 0.3413,
+      "step": 680
+    },
+    {
+      "epoch": 0.28085661266863937,
+      "grad_norm": 0.8011920131999447,
+      "learning_rate": 4.5217189042619345e-05,
+      "loss": 0.3389,
+      "step": 700
+    },
+    {
+      "epoch": 0.28888108731631473,
+      "grad_norm": 0.8067168553032359,
+      "learning_rate": 4.4797361763230224e-05,
+      "loss": 0.3185,
+      "step": 720
+    },
+    {
+      "epoch": 0.29690556196399015,
+      "grad_norm": 0.6665228849255169,
+      "learning_rate": 4.436200059799121e-05,
+      "loss": 0.3232,
+      "step": 740
+    },
+    {
+      "epoch": 0.30493003661166557,
+      "grad_norm": 0.6617968011184702,
+      "learning_rate": 4.391144715053238e-05,
+      "loss": 0.318,
+      "step": 760
+    },
+    {
+      "epoch": 0.312954511259341,
+      "grad_norm": 0.7925748113649975,
+      "learning_rate": 4.344605494502053e-05,
+      "loss": 0.3438,
+      "step": 780
+    },
+    {
+      "epoch": 0.3209789859070164,
+      "grad_norm": 0.7874288584383095,
+      "learning_rate": 4.2966189148768474e-05,
+      "loss": 0.3218,
+      "step": 800
+    },
+    {
+      "epoch": 0.3290034605546918,
+      "grad_norm": 0.5964012085577759,
+      "learning_rate": 4.247222628570862e-05,
+      "loss": 0.325,
+      "step": 820
+    },
+    {
+      "epoch": 0.33702793520236723,
+      "grad_norm": 0.7901232690113225,
+      "learning_rate": 4.196455394095561e-05,
+      "loss": 0.3259,
+      "step": 840
+    },
+    {
+      "epoch": 0.34505240985004265,
+      "grad_norm": 0.6161692661704234,
+      "learning_rate": 4.144357045668993e-05,
+      "loss": 0.3282,
+      "step": 860
+    },
+    {
+      "epoch": 0.353076884497718,
+      "grad_norm": 0.7071927191922839,
+      "learning_rate": 4.0909684619601e-05,
+      "loss": 0.3215,
+      "step": 880
+    },
+    {
+      "epoch": 0.36110135914539343,
+      "grad_norm": 0.7540766905998272,
+      "learning_rate": 4.036331534013502e-05,
+      "loss": 0.3141,
+      "step": 900
+    },
+    {
+      "epoch": 0.36912583379306885,
+      "grad_norm": 0.7828196756015018,
+      "learning_rate": 3.980489132379937e-05,
+      "loss": 0.3099,
+      "step": 920
+    },
+    {
+      "epoch": 0.37715030844074426,
+      "grad_norm": 0.7665378450501007,
+      "learning_rate": 3.923485073478123e-05,
+      "loss": 0.3154,
+      "step": 940
+    },
+    {
+      "epoch": 0.3851747830884197,
+      "grad_norm": 0.7064791446421703,
+      "learning_rate": 3.8653640852144643e-05,
+      "loss": 0.3192,
+      "step": 960
+    },
+    {
+      "epoch": 0.3931992577360951,
+      "grad_norm": 0.6894942843454174,
+      "learning_rate": 3.80617177188755e-05,
+      "loss": 0.3274,
+      "step": 980
+    },
+    {
+      "epoch": 0.4012237323837705,
+      "grad_norm": 0.6747469008968356,
+      "learning_rate": 3.745954578405012e-05,
+      "loss": 0.3216,
+      "step": 1000
+    },
+    {
+      "epoch": 0.40924820703144593,
+      "grad_norm": 0.8112185519554851,
+      "learning_rate": 3.684759753840789e-05,
+      "loss": 0.3239,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4172726816791213,
+      "grad_norm": 0.6811337824140572,
+      "learning_rate": 3.622635314361416e-05,
+      "loss": 0.3125,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4252971563267967,
+      "grad_norm": 0.7484799717463894,
+      "learning_rate": 3.559630005550416e-05,
+      "loss": 0.3209,
+      "step": 1060
+    },
+    {
+      "epoch": 0.4333216309744721,
+      "grad_norm": 0.6914997047255979,
+      "learning_rate": 3.495793264160359e-05,
+      "loss": 0.3061,
+      "step": 1080
+    },
+    {
+      "epoch": 0.44134610562214754,
+      "grad_norm": 0.6177004112053062,
+      "learning_rate": 3.4311751793225964e-05,
+      "loss": 0.3081,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44937058026982296,
+      "grad_norm": 0.7656940899490844,
+      "learning_rate": 3.365826453245115e-05,
+      "loss": 0.3258,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4573950549174984,
+      "grad_norm": 0.7072757457639977,
+      "learning_rate": 3.2997983614293404e-05,
+      "loss": 0.3158,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4654195295651738,
+      "grad_norm": 0.7029721091978121,
+      "learning_rate": 3.2331427124371115e-05,
+      "loss": 0.3155,
+      "step": 1160
+    },
+    {
+      "epoch": 0.4734440042128492,
+      "grad_norm": 0.742312775553165,
+      "learning_rate": 3.1659118072393906e-05,
+      "loss": 0.3151,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4814684788605246,
+      "grad_norm": 0.7586510237201778,
+      "learning_rate": 3.098158398178606e-05,
+      "loss": 0.2921,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4894929535082,
+      "grad_norm": 0.6302386060292237,
+      "learning_rate": 3.0299356475768326e-05,
+      "loss": 0.3042,
+      "step": 1220
+    },
+    {
+      "epoch": 0.4975174281558754,
+      "grad_norm": 0.7177873646521117,
+      "learning_rate": 2.9612970860222816e-05,
+      "loss": 0.3074,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5055419028035508,
+      "grad_norm": 0.6442414947030823,
+      "learning_rate": 2.8922965703668337e-05,
+      "loss": 0.3047,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5135663774512262,
+      "grad_norm": 0.7076061109007938,
+      "learning_rate": 2.8229882414675672e-05,
+      "loss": 0.3033,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5215908520989017,
+      "grad_norm": 0.6578079486576341,
+      "learning_rate": 2.75342648170545e-05,
+      "loss": 0.3051,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5296153267465771,
+      "grad_norm": 0.7945155922763601,
+      "learning_rate": 2.6836658723145175e-05,
+      "loss": 0.2967,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5376398013942525,
+      "grad_norm": 0.6487682986757239,
+      "learning_rate": 2.613761150555019e-05,
+      "loss": 0.3044,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5456642760419279,
+      "grad_norm": 0.6958050009061036,
+      "learning_rate": 2.5437671667641445e-05,
+      "loss": 0.3061,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5536887506896033,
+      "grad_norm": 0.6266867011506455,
+      "learning_rate": 2.4737388413180217e-05,
+      "loss": 0.2897,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5617132253372787,
+      "grad_norm": 0.7124320790824831,
+      "learning_rate": 2.403731121538762e-05,
+      "loss": 0.2862,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5697376999849542,
+      "grad_norm": 0.7470494242121043,
+      "learning_rate": 2.3337989385803567e-05,
+      "loss": 0.3018,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5777621746326295,
+      "grad_norm": 0.6734120153458941,
+      "learning_rate": 2.2639971643272688e-05,
+      "loss": 0.2927,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5857866492803049,
+      "grad_norm": 0.6694340995198956,
+      "learning_rate": 2.194380568339519e-05,
+      "loss": 0.2912,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5938111239279803,
+      "grad_norm": 0.6416254443296999,
+      "learning_rate": 2.1250037748780706e-05,
+      "loss": 0.2833,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6018355985756557,
+      "grad_norm": 0.6576796287869531,
+      "learning_rate": 2.0559212200442152e-05,
+      "loss": 0.3005,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6098600732233311,
+      "grad_norm": 0.7534672667085268,
+      "learning_rate": 1.9871871090666023e-05,
+      "loss": 0.2902,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6178845478710066,
+      "grad_norm": 0.683888843023483,
+      "learning_rate": 1.9188553737694142e-05,
+      "loss": 0.2802,
+      "step": 1540
+    },
+    {
+      "epoch": 0.625909022518682,
+      "grad_norm": 0.6505090735155789,
+      "learning_rate": 1.8509796302550763e-05,
+      "loss": 0.287,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6339334971663574,
+      "grad_norm": 0.7052076493927231,
+      "learning_rate": 1.783613136834688e-05,
+      "loss": 0.281,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6419579718140328,
+      "grad_norm": 0.6384510613508823,
+      "learning_rate": 1.7168087522391958e-05,
+      "loss": 0.2763,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6499824464617082,
+      "grad_norm": 0.6633378463426743,
+      "learning_rate": 1.6506188941440958e-05,
+      "loss": 0.285,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6580069211093836,
+      "grad_norm": 0.6982839509670195,
+      "learning_rate": 1.585095498040205e-05,
+      "loss": 0.2804,
+      "step": 1640
+    },
+    {
+      "epoch": 0.666031395757059,
+      "grad_norm": 0.6270272887976673,
+      "learning_rate": 1.5202899764827799e-05,
+      "loss": 0.2785,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6740558704047345,
+      "grad_norm": 0.6172418320458167,
+      "learning_rate": 1.4562531787509504e-05,
+      "loss": 0.2734,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6820803450524099,
+      "grad_norm": 0.7230716801753746,
+      "learning_rate": 1.3930353509491225e-05,
+      "loss": 0.2921,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6901048197000853,
+      "grad_norm": 0.624829631926983,
+      "learning_rate": 1.3306860965816687e-05,
+      "loss": 0.2745,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6981292943477607,
+      "grad_norm": 0.6057171773833744,
+      "learning_rate": 1.2692543376318172e-05,
+      "loss": 0.2812,
+      "step": 1740
+    },
+    {
+      "epoch": 0.706153768995436,
+      "grad_norm": 0.6600106987481957,
+      "learning_rate": 1.2087882761753052e-05,
+      "loss": 0.2762,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7141782436431114,
+      "grad_norm": 0.6513027790812009,
+      "learning_rate": 1.1493353565588946e-05,
+      "loss": 0.2824,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7222027182907869,
+      "grad_norm": 0.6464858105319229,
+      "learning_rate": 1.0909422281734372e-05,
+      "loss": 0.2772,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7302271929384623,
+      "grad_norm": 0.5987416675990789,
+      "learning_rate": 1.033654708850704e-05,
+      "loss": 0.2729,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7382516675861377,
+      "grad_norm": 0.6700627827898618,
+      "learning_rate": 9.775177489126839e-06,
+      "loss": 0.2662,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7462761422338131,
+      "grad_norm": 0.6252184614146273,
+      "learning_rate": 9.225753959015726e-06,
+      "loss": 0.2757,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7543006168814885,
+      "grad_norm": 0.6775143307950428,
+      "learning_rate": 8.688707600181237e-06,
+      "loss": 0.2714,
+      "step": 1880
+    },
+    {
+      "epoch": 0.762325091529164,
+      "grad_norm": 0.6952554867252799,
+      "learning_rate": 8.164459802954771e-06,
+      "loss": 0.2782,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7703495661768394,
+      "grad_norm": 0.6783881222495053,
+      "learning_rate": 7.653421915350096e-06,
+      "loss": 0.2699,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7783740408245148,
+      "grad_norm": 0.6556587479775633,
+      "learning_rate": 7.1559949203015005e-06,
+      "loss": 0.2674,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7863985154721902,
+      "grad_norm": 0.7269086771080256,
+      "learning_rate": 6.67256912103485e-06,
+      "loss": 0.2696,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7944229901198656,
+      "grad_norm": 0.6782398065845676,
+      "learning_rate": 6.203523834818395e-06,
+      "loss": 0.2616,
+      "step": 1980
+    },
+    {
+      "epoch": 0.802447464767541,
+      "grad_norm": 0.6401864638918741,
+      "learning_rate": 5.749227095333684e-06,
+      "loss": 0.2727,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8104719394152164,
+      "grad_norm": 0.6920549327363028,
+      "learning_rate": 5.310035363900029e-06,
+      "loss": 0.2613,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8184964140628919,
+      "grad_norm": 0.7544225062042402,
+      "learning_rate": 4.886293249779203e-06,
+      "loss": 0.2649,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8265208887105673,
+      "grad_norm": 0.7784252166653262,
+      "learning_rate": 4.4783332397797725e-06,
+      "loss": 0.2646,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8345453633582426,
+      "grad_norm": 0.7372167602245259,
+      "learning_rate": 4.086475437373222e-06,
+      "loss": 0.2663,
+      "step": 2080
+    },
+    {
+      "epoch": 0.842569838005918,
+      "grad_norm": 0.5940476502560079,
+      "learning_rate": 3.711027311526605e-06,
+      "loss": 0.2474,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8505943126535934,
+      "grad_norm": 0.7426516397535643,
+      "learning_rate": 3.3522834554488265e-06,
+      "loss": 0.2667,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8586187873012688,
+      "grad_norm": 0.6474191378185361,
+      "learning_rate": 3.010525355439739e-06,
+      "loss": 0.2633,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8666432619489443,
+      "grad_norm": 0.7138316369428281,
+      "learning_rate": 2.6860211700235616e-06,
+      "loss": 0.2653,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8746677365966197,
+      "grad_norm": 0.7205767765435191,
+      "learning_rate": 2.3790255195398293e-06,
+      "loss": 0.269,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8826922112442951,
+      "grad_norm": 0.6866728998175627,
+      "learning_rate": 2.0897792863570133e-06,
+      "loss": 0.2781,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8907166858919705,
+      "grad_norm": 0.6386115100985029,
+      "learning_rate": 1.818509425865561e-06,
+      "loss": 0.248,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8987411605396459,
+      "grad_norm": 0.5816063089909334,
+      "learning_rate": 1.5654287883986568e-06,
+      "loss": 0.2495,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9067656351873213,
+      "grad_norm": 0.6044106984921237,
+      "learning_rate": 1.3307359522204187e-06,
+      "loss": 0.2546,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9147901098349968,
+      "grad_norm": 0.6487114272956552,
+      "learning_rate": 1.1146150677126321e-06,
+      "loss": 0.2493,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9228145844826722,
+      "grad_norm": 0.7113121988343898,
+      "learning_rate": 9.172357128822001e-07,
+      "loss": 0.2649,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9308390591303476,
+      "grad_norm": 0.684922616701092,
+      "learning_rate": 7.387527603027383e-07,
+      "loss": 0.2619,
+      "step": 2320
+    },
+    {
+      "epoch": 0.938863533778023,
+      "grad_norm": 0.6512571317668248,
+      "learning_rate": 5.793062555946999e-07,
+      "loss": 0.2626,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9468880084256984,
+      "grad_norm": 0.9231979423940574,
+      "learning_rate": 4.390213075393973e-07,
+      "loss": 0.268,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9549124830733738,
+      "grad_norm": 0.5874482600389693,
+      "learning_rate": 3.1800798991309944e-07,
+      "loss": 0.2627,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9629369577210491,
+      "grad_norm": 0.827108940722453,
+      "learning_rate": 2.163612551182942e-07,
+      "loss": 0.2586,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9709614323687246,
+      "grad_norm": 0.5907349717505673,
+      "learning_rate": 1.3416085967982994e-07,
+      "loss": 0.2642,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9789859070164,
+      "grad_norm": 0.7334026096749088,
+      "learning_rate": 7.14713016644053e-08,
+      "loss": 0.2649,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9870103816640754,
+      "grad_norm": 0.523367756897521,
+      "learning_rate": 2.8341770072548567e-08,
+      "loss": 0.2682,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9950348563117508,
+      "grad_norm": 0.6000740449055824,
+      "learning_rate": 4.806106242741249e-09,
+      "loss": 0.2627,
+      "step": 2480
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2493,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 41482954211328.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c84e7d82c69cf43358bb1ce05781e7a58918dc28fa488928c30ee7874356db9
+size 8145